Modern online advertising systems often involve a substantial number of advertisers in each auction, which results in scalability issues. To address this challenge, two-stage auctions have been designed and implemented in practice. These auctions enable efficient allocation of ad slots among numerous candidate advertisers in a short response time. This approach employs a fast yet coarse model in the first stage to select a small subset of advertisers, followed by a slow, more refined model to determine the final winners. However, existing two-stage auction mechanisms primarily focus on optimizing welfare, overlooking other critical objectives of the platform, such as revenue.

We present a new solution to the fine-grained retrieval of clean CAD models from a large-scale database in order to recover detailed object shape geometries for RGBD scans. Unlike previous work simply indexing into a moderately small database using an object shape descriptor and accepting the top retrieval result, we argue that in the case of a large-scale database a more accurate model may be found within a neighborhood of the descriptor. More importantly, we propose that the distinctiveness deficiency of shape descriptors at the instance level can be compensated by a geometry-based re-ranking of its neighborhood. Our approach first leverages the discriminative power of learned representations to distinguish between different categories of models and then uses a novel robust point set distance metric to re-rank the CAD neighbor-hood, enabling fine-grained retrieval in a large shape database. Evaluation on a real-world dataset shows that our geometry-based re-ranking is a conceptually simple but highly effective method that can lead to a significant improvement in retrieval accuracy compared to the state-of-the-art.

We introduce a new solution to point set registration, a fundamental geometric problem occurring in many computer vision and robotics applications. We consider the specific case in which the point sets are segmented into semantically annotated parts. Such information may for example come from object detection or instance-level semantic segmentation in a registered RGB image. Existing methods incorporate the additional information to restrict or re-weight the point-pair associations occurring throughout the registration process. We introduce a novel hierarchical association framework for a simultaneous inference of semantic region association likelihoods. The formulation is elegantly solved using cascaded expectation-maximization. We conclude by demonstrating a substantial improvement over existing alternatives on open RGBD datasets.

We present a tightly-coupled multi-sensor fusion architecture for autonomous vehicle applications, which achieves centimetre-level accuracy and high robustness in various scenarios. In order to realize robust and accurate point-cloud feature matching we propose a novel method for extracting structural, highly discriminative features from LiDAR point clouds. For high frequency motion prediction and noise propagation, we use incremental on-manifold IMU pre-integration. We also adopt a multi-frame sliding window square root inverse filter, so that the system maintains numerically stable results under the premise of limited power consumption. To verify our methodology, we test the fusion algorithm in multiple applications and platforms equipped with a LiDAR-IMU system. Our results demonstrate that our fusion framework attains state-of-the-art localization accuracy, high robustness and a good generalization ability.

The increasing availability of surround-view camera systems in passenger vehicles motivates their use as an exterior perception modality for intelligent vehicle behaviour. An important problem within this context is the extrinsic calibration between the cameras, which is challenging due to the often reduced overlap between the fields of view of neighbouring views. Our work is motivated by two insights. First, we argue that the accuracy of vision-based vehicle motion estimation depends crucially on the quality of exterior orientation calibration, while design parameters for camera positions typically provide sufficient accuracy. Second, we demonstrate how planar vehicle motion related direction vectors can be used to accurately identify individual camera-to-vehicle rotations, which are more useful than the commonly and tediously derived camera-to-camera transformations. We present a complete and highly practicable online optimisation strategy to obtain the exterior orientation parameters and conclude with successful tests on simulated, indoor, and large-scale outdoor experiments.

Over the past decade, the Gröbner basis theory and automatic solver generation have lead to a large number of solutions to geometric vision problems. In practically all cases, the derived solvers apply a fixed elimination template to calculate the Groebner basis and thereby identify the zero-dimensional variety of the original polynomial constraints. However, it is clear that different variable or monomial orderings lead to different elimination templates, and we show that they may present a large variability in accuracy for a certain instance of a problem. The present paper has two contributions. We first show that for a common class of problems in geometric vision, variable reordering simply translates into a permutation of the columns of the initial coefficient matrix, and that-as a result-one and the same elimination template can be reused in different ways, each one leading to potentially different accuracy. We then prove that the original set of coefficients may contain sufficient information to train a classifier for online selection of a good solver, most notably at the cost of only a small computational overhead. We demonstrate wide applicability at the hand of generic dense polynomial problem solvers, as well as a concrete solver from geometric vision.

Direct-sequence spread-spectrum (DS/SS) receivers are based generally on correlation techniques, such as the matched filter (MF). These methods are optimal for the despreading of the PN code in the presence of Gaussian noise. In the multipath propagation environment, this processing gain is insufficient to reject effectively cochannel and multipath delay interference. This restricts the performance of the acquisition system and hence, of the receiver. Cancellation techniques can be used before acquisition, but this does not provide significant improvement in the case of the multipath delay and fading environment. A new channel filter to be used before the acquisition system is proposed to overcome the multi-user and multi-path delay interference. A simulator is used to evaluate and compare the performance in terms of multiple users and multi-path delay both with and without proposed channel filter. Details of the system configuration, the design concept of the proposed new channel filter and the simulation technique are discussed. The results show that the proposed new technique can significantly improve the overall system performance.>